opencode-runner SKILL.md skillB

opencode-runner from luongnv89/skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add luongnv89/skills/opencode-runner@v1.6.0

Pins v1.6.0 in mdr.lock. Pin the fingerprint instead.

Audit grade
B, 16 of 17 checks passed
Kind
SKILL.md skill
Repository
luongnv89/skills
Path
skills/opencode-runner/SKILL.md
Versions recorded
5
Latest version
v1.6.0, committed Oct 6, 2026
First version recorded
Jul 1, 2026
Size
18,244 bytes
Repository stars
133
License
MIT

Run coding tasks via opencode using free cloud models. Use when asked to offload work to opencode.ai or run a free model. Don't use for local models (Ollama, LM Studio), Claude/OpenAI calls, or when Claude should do the work itself.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# OpenCode Runner

Delegate coding tasks to opencode using free models — zero cost, fully automated.

OpenCode (opencode.ai) is a terminal AI coding assistant that supports multiple providers and models. This skill automates the process of selecting the best available free model, launching the task, and reporting progress back to you.

## Prerequisites

- **opencode installed**: `which opencode` must succeed; install via `npm i -g opencode-ai@latest` or `brew install opencode` if missing
- **Internet access**: required for cloud model selection and task execution via OpenCode Zen
- **Project context**: the current working directory should be the project root for file-context tasks

## Critical Rules

1. **Never do the task yourself.** This skill exists solely to delegate work to opencode. If opencode is not installed, fails to run, or no free cloud model is available — report the problem to the user and **stop**. Do not fall back to editing files directly, writing code yourself, or using any other tool to accomplish the user's coding task. The whole point is that opencode does the work.
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add luongnv89/skills/opencode-runner@sha256:cf4d50d25e7f099e

The line at the top of this page pins the label v1.6.0, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_oek6wpo6c3eyzicp.svg)](https://markdownregistry.com/a/art_oek6wpo6c3eyzicp)

3 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 5 versions of this file, between Jul 1, 2026 and Oct 6, 2026, about one every 24 days.

versioncommittedcommitsizeaudit
v1.6.0 latest2026-10-06 5c14be1 18,244 BB view · diff
v1.5.12026-09-26 1b73d31 17,600 BB view · diff
v1.5.02026-09-05 b420157 17,611 BB view · diff
v1.4.22026-08-31 8f25f94 16,844 BB view · diff
v1.4.12026-07-01 31a605a 16,842 BB view

Audit of the latest version

B  16 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • fail: No curl or wget piped into a shell (matched: curl -fsSL https://opencode.ai/install | bash)
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (18244 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Starting a new one? Use a template for SKILL.md on mdpantry, which passes every one of these checks and says what to change in it.

Source

GitHub

luongnv89/skills · 133 stars · license MIT · pushed 2026-10-20 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_oek6wpo6c3eyzicp
GET https://markdownregistry.com/api/v1/resolve?ref=luongnv89/skills/opencode-runner
GET https://markdownregistry.com/api/v1/blob/cf4d50d25e7f099edef4d89be94b494c33d8b6349eee99c523be63afa321e621

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from luongnv89/skills

AGENTS.md AGENTS.md file
luongnv89/skills · AGENTS.md
git:20261010.f8bb4a8 · audit A · 133 stars
CLAUDE.md CLAUDE.md file
luongnv89/skills · CLAUDE.md
git:20261001.c1c53b9 · audit B · 133 stars
agent-config SKILL.md skill
luongnv89/skills · skills/agent-config/SKILL.md · Create, update, or audit AGENTS.md (default) or CLAUDE.md agent instructions: set up, prune, add a rule, or merge…
v2.2.0 · audit A · 133 stars
ai-job-scout SKILL.md skill
luongnv89/skills · skills/ai-job-scout/SKILL.md · Find open AI engineering jobs that fit a candidate, verify location and apply links, and assess each employer's…
v1.1.1 · audit A · 133 stars
appstore-assets SKILL.md skill
luongnv89/skills · skills/appstore-assets/SKILL.md · Generate App Store screenshots and header/search images for iPhone, iPad and Mac from a codebase or landing page, or…
v1.0.0 · audit A · 133 stars
appstore-review-checker SKILL.md skill
luongnv89/skills · skills/appstore-review-checker/SKILL.md · Audit iOS/macOS apps against App Store Review Guidelines before submission, with evidence-backed verdicts and fixes…
v1.5.0 · audit A · 133 stars
aso-marketing SKILL.md skill
luongnv89/skills · skills/aso-marketing/SKILL.md · Optimize App Store and Google Play listings via a 7-phase, plan-approval-gated ASO workflow (keyword strategy…
v1.4.0 · audit A · 133 stars
auto-push SKILL.md skill
luongnv89/skills · skills/auto-push/SKILL.md · Generate a commit message, stage all changes, and push to remote after scanning for secrets, large files, and…
v1.1.1 · audit A · 133 stars
brand-name-checker SKILL.md skill
luongnv89/skills · skills/brand-name-checker/SKILL.md · Check product and brand names for conflicts across trademarks, domains, social handles, and package registries. Returns…
v1.5.0 · audit A · 133 stars
cleanup-project SKILL.md skill
luongnv89/skills · skills/cleanup-project/SKILL.md · Prepare a git repo before new work: review uncommitted changes, fix .gitignore, delete merged branches, end on clean…
v1.0.2 · audit A · 133 stars
cli-builder SKILL.md skill
luongnv89/skills · skills/cli-builder/SKILL.md · Build production-quality CLIs with language detection and a five-step approval-gated workflow. Use when wrapping an…
v1.3.0 · audit A · 133 stars
code-review SKILL.md skill
luongnv89/skills · skills/code-review/SKILL.md · Review or improve code — one skill, four modes: bug/security review (default), performance, clean-code audit, slop…
v2.2.2 · audit A · 133 stars

Every file in luongnv89/skills

Browse by kind, by grade B, or by owner.